from openai import OpenAI
client = OpenAI(
base_url="http://localhost:8000/v1",
api_key="EMPTY"
)
# Define available tools
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "Temperature unit"
}
},
"required": ["location"]
}
}
}
]
# Make request with streaming to see thinking process
response = client.chat.completions.create(
model="openai/gpt-oss-120b",
messages=[
{"role": "user", "content": "What's the weather in Beijing?"}
],
tools=tools,
temperature=0.7,
stream=True
)
# Process streaming response
thinking_started = False
has_thinking = False
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
# Print thinking process
if hasattr(delta, 'reasoning_content') and delta.reasoning_content:
if not thinking_started:
print("=============== Thinking =================", flush=True)
thinking_started = True
has_thinking = True
print(delta.reasoning_content, end="", flush=True)
# Print tool calls
if hasattr(delta, 'tool_calls') and delta.tool_calls:
# Close thinking section if needed
if has_thinking and thinking_started:
print("\n=============== Content =================", flush=True)
thinking_started = False
for tool_call in delta.tool_calls:
if tool_call.function:
print(f"🔧 Tool Call: {tool_call.function.name}")
print(f" Arguments: {tool_call.function.arguments}")
# Print content
if delta.content:
print(delta.content, end="", flush=True)
print()
